Epileptiform discharges detection from eeg signals using grouped-channel restricted band analysis

Sheng Chih Yang, Sheng Hsing Lan, Han Yen Chang, Pau-Choo Chung

Research output: Contribution to journalArticle

Abstract

Epileptiform activities can be detected by scanning the electroencephalogram (EEG) signals of an epileptic patient. Since EEG provides multi-channel signals, it is an opportunity to employ multi-spectrum signal processing techniques for improving the accuracy of signal separation or feature extraction. Although multi-channel signals provide stronger characteristics than a single signal for feature extraction, taking all of the EEG signals into consideration may interfere with the accuracy of epileptiform discharge detection because a part of the signals that do not contain the epileptic activity will be treated as noise. In this paper, we developed a new signature analysis scheme, grouped-channel restricted band analysis (GRBA), for interictal epileptiform discharges (IED) detection from EEG signals. Unlike most traditional epileptic activity detection techniques that inaccurately take single or all EEG signals into consideration, GRBA simultaneously considers three important characteristics of epileptiform discharge waves, i.e. multispectral, finite spread, and specific duration, to detect epileptiform discharges efficiently. A series of experiments were conducted to compare GRBA with traditional feature-classifier methods and the non-grouped approach to evaluate this novel approach by the correct detection rate (Rc) and receiver operating characteristic (ROC) curves. The experimental results showed that our new signature analysis scheme, GRBA, had a superior quality. Moreover, we observed that the area under ROC curves and the Rc for GRBA were as high as 0.9479 and 94.1%, respectively.

Original languageEnglish
Article number1550014
JournalBiomedical Engineering - Applications, Basis and Communications
Volume27
Issue number2
DOIs
Publication statusPublished - 2015 Apr 25

Fingerprint

Electroencephalography
ROC Curve
Feature extraction
Noise
Signal processing
Classifiers
Scanning
Experiments

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Bioengineering
  • Biomedical Engineering

Cite this

@article{c01f535e758245528c468a54bdff6b37,
title = "Epileptiform discharges detection from eeg signals using grouped-channel restricted band analysis",
abstract = "Epileptiform activities can be detected by scanning the electroencephalogram (EEG) signals of an epileptic patient. Since EEG provides multi-channel signals, it is an opportunity to employ multi-spectrum signal processing techniques for improving the accuracy of signal separation or feature extraction. Although multi-channel signals provide stronger characteristics than a single signal for feature extraction, taking all of the EEG signals into consideration may interfere with the accuracy of epileptiform discharge detection because a part of the signals that do not contain the epileptic activity will be treated as noise. In this paper, we developed a new signature analysis scheme, grouped-channel restricted band analysis (GRBA), for interictal epileptiform discharges (IED) detection from EEG signals. Unlike most traditional epileptic activity detection techniques that inaccurately take single or all EEG signals into consideration, GRBA simultaneously considers three important characteristics of epileptiform discharge waves, i.e. multispectral, finite spread, and specific duration, to detect epileptiform discharges efficiently. A series of experiments were conducted to compare GRBA with traditional feature-classifier methods and the non-grouped approach to evaluate this novel approach by the correct detection rate (Rc) and receiver operating characteristic (ROC) curves. The experimental results showed that our new signature analysis scheme, GRBA, had a superior quality. Moreover, we observed that the area under ROC curves and the Rc for GRBA were as high as 0.9479 and 94.1{\%}, respectively.",
author = "Yang, {Sheng Chih} and Lan, {Sheng Hsing} and Chang, {Han Yen} and Pau-Choo Chung",
year = "2015",
month = "4",
day = "25",
doi = "10.4015/S1016237215500143",
language = "English",
volume = "27",
journal = "Biomedical Engineering - Applications, Basis and Communications",
issn = "1016-2372",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

Epileptiform discharges detection from eeg signals using grouped-channel restricted band analysis. / Yang, Sheng Chih; Lan, Sheng Hsing; Chang, Han Yen; Chung, Pau-Choo.

In: Biomedical Engineering - Applications, Basis and Communications, Vol. 27, No. 2, 1550014, 25.04.2015.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Epileptiform discharges detection from eeg signals using grouped-channel restricted band analysis

AU - Yang, Sheng Chih

AU - Lan, Sheng Hsing

AU - Chang, Han Yen

AU - Chung, Pau-Choo

PY - 2015/4/25

Y1 - 2015/4/25

N2 - Epileptiform activities can be detected by scanning the electroencephalogram (EEG) signals of an epileptic patient. Since EEG provides multi-channel signals, it is an opportunity to employ multi-spectrum signal processing techniques for improving the accuracy of signal separation or feature extraction. Although multi-channel signals provide stronger characteristics than a single signal for feature extraction, taking all of the EEG signals into consideration may interfere with the accuracy of epileptiform discharge detection because a part of the signals that do not contain the epileptic activity will be treated as noise. In this paper, we developed a new signature analysis scheme, grouped-channel restricted band analysis (GRBA), for interictal epileptiform discharges (IED) detection from EEG signals. Unlike most traditional epileptic activity detection techniques that inaccurately take single or all EEG signals into consideration, GRBA simultaneously considers three important characteristics of epileptiform discharge waves, i.e. multispectral, finite spread, and specific duration, to detect epileptiform discharges efficiently. A series of experiments were conducted to compare GRBA with traditional feature-classifier methods and the non-grouped approach to evaluate this novel approach by the correct detection rate (Rc) and receiver operating characteristic (ROC) curves. The experimental results showed that our new signature analysis scheme, GRBA, had a superior quality. Moreover, we observed that the area under ROC curves and the Rc for GRBA were as high as 0.9479 and 94.1%, respectively.

AB - Epileptiform activities can be detected by scanning the electroencephalogram (EEG) signals of an epileptic patient. Since EEG provides multi-channel signals, it is an opportunity to employ multi-spectrum signal processing techniques for improving the accuracy of signal separation or feature extraction. Although multi-channel signals provide stronger characteristics than a single signal for feature extraction, taking all of the EEG signals into consideration may interfere with the accuracy of epileptiform discharge detection because a part of the signals that do not contain the epileptic activity will be treated as noise. In this paper, we developed a new signature analysis scheme, grouped-channel restricted band analysis (GRBA), for interictal epileptiform discharges (IED) detection from EEG signals. Unlike most traditional epileptic activity detection techniques that inaccurately take single or all EEG signals into consideration, GRBA simultaneously considers three important characteristics of epileptiform discharge waves, i.e. multispectral, finite spread, and specific duration, to detect epileptiform discharges efficiently. A series of experiments were conducted to compare GRBA with traditional feature-classifier methods and the non-grouped approach to evaluate this novel approach by the correct detection rate (Rc) and receiver operating characteristic (ROC) curves. The experimental results showed that our new signature analysis scheme, GRBA, had a superior quality. Moreover, we observed that the area under ROC curves and the Rc for GRBA were as high as 0.9479 and 94.1%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=84928474219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928474219&partnerID=8YFLogxK

U2 - 10.4015/S1016237215500143

DO - 10.4015/S1016237215500143

M3 - Article

VL - 27

JO - Biomedical Engineering - Applications, Basis and Communications

JF - Biomedical Engineering - Applications, Basis and Communications

SN - 1016-2372

IS - 2

M1 - 1550014

ER -